Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 700 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.6735. Min Act: -0.0000

Data Index: 1269978 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1280668 (The Pile)

Max Activating Token Index: 243

Text #2

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.5355. Min Act: -0.0000

Data Index: 854282 (The Pile)

Max Activating Token Index: 623

Text #3

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.5591. Min Act: -0.0000

Data Index: 56093 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.4784. Min Act: -0.0000

Data Index: 823982 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.4911. Min Act: -0.0000

Data Index: 1200146 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.4428. Min Act: -0.0000

Data Index: 1648651 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.4244. Min Act: -0.0000

Data Index: 392292 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.4307. Min Act: -0.0000

Data Index: 310273 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.4109. Min Act: -0.0000

Data Index: 1775455 (The Pile)

Max Activating Token Index: 71

Text #10

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.3350. Min Act: -0.0000

Data Index: 861309 (The Pile)

Max Activating Token Index: 946

Text #11

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.3526. Min Act: -0.0000

Data Index: 1545086 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.3086. Min Act: -0.0000

Data Index: 1391230 (The Pile)

Max Activating Token Index: 313

Text #13

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.4023. Min Act: -0.0000

Data Index: 1267891 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.3006. Min Act: -0.0000

Data Index: 1477570 (The Pile)

Max Activating Token Index: 734

Text #15

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.2589. Min Act: -0.0000

Data Index: 217574 (The Pile)

Max Activating Token Index: 946

Text #16

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1713692 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1171163 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.2487. Min Act: -0.0000

Data Index: 903516 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1068494 (The Pile)

Max Activating Token Index: 73